Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Group Polarization01:01

Group Polarization

39.2K
Group polarization is the strengthening of an original group attitude following the discussion of views within a group (Teger & Pruitt, 1967). That is, if a group initially favors a viewpoint, after discussion the group consensus is likely a stronger endorsement of the viewpoint. Conversely, if the group was initially opposed to a viewpoint, group discussion would likely lead to stronger opposition.
39.2K
Convolution Properties II01:17

Convolution Properties II

587
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
587
Molecular Shape and Polarity03:37

Molecular Shape and Polarity

75.7K
Dipole Moment of a Molecule
75.7K
Protein Networks02:26

Protein Networks

4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
Convolution Properties I01:20

Convolution Properties I

602
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
602
Classification of Titrimetric Analysis Based on Reaction Types01:01

Classification of Titrimetric Analysis Based on Reaction Types

1.8K
Titrimetric analysis in solution chemistry involves measuring the volume of solutions and is often called volumetric analysis. The standard solution of known concentration in the burette is called the titrant, whereas the solution of unknown concentration in the flask is called the analyte, or titrand. Titrimetric analyses can be classified into four types based on the reactions between the titrant and analyte.
Titrations between an acid and a base lead to neutralization reactions that form...
1.8K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Characterization of mucus plugging in patients with chronic obstructive pulmonary disease: additional clinical significance of asthma-like features.

BMC pulmonary medicine·2026
Same author

JCS/JPCPHS 2025 Guideline on Pulmonary Hypertension and Pulmonary Embolism/Deep Vein Thrombosis.

Circulation journal : official journal of the Japanese Circulation Society·2026
Same author

Prognostic impact of <sup>18</sup>F-fluorodeoxyglucose positron emission tomography and cardiac magnetic resonance-proven cardiac involvement in pulmonary sarcoidosis: a single centre long-term cohort study.

BMC pulmonary medicine·2026
Same author

Efficacy of short-term, low-dose pulmonary vasodilators for chronic thromboembolic pulmonary hypertension: a retrospective pilot study.

Respiratory investigation·2026
Same author

Interpretation of myocardial FDG uptake during corticosteroid therapy in cardiac sarcoidosis evaluation with <sup>18</sup>F-FDG PET/CT.

Annals of nuclear medicine·2026
Same author

Somatostatin receptor expression for peptide receptor radionuclide therapy in Japanese patients with recurrent or metastatic differentiated thyroid cancer.

Annals of nuclear medicine·2026

Related Experiment Video

Updated: Feb 2, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K

Cardiac sarcoidosis classification with deep convolutional neural network-based features using polar maps.

Ren Togo1, Kenji Hirata2, Osamu Manabe2

  • 1Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, 060-0814, Japan.

Computers in Biology and Medicine
|November 18, 2018
PubMed
Summary

Deep convolutional neural network (DCNN) features effectively differentiate cardiac sarcoidosis (CS) from non-CS using polar maps. This DCNN approach shows superior performance compared to conventional quantitative analysis methods for CS classification.

Keywords:
(18)F-FDG PETCardiac sarcoidosis (CS)Computer-aided diagnosisConvolutional neural network (CNN)Deep learningFeature extractionFeature selectionMachine learningRadiology

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K
A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

7.1K

Related Experiment Videos

Last Updated: Feb 2, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K
A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

7.1K

Area of Science:

  • Cardiology
  • Radiology
  • Artificial Intelligence

Background:

  • Cardiac sarcoidosis (CS) diagnosis can be challenging.
  • Polar maps derived from PET/CT images offer a visual representation of cardiac function.
  • Differentiating CS from non-CS is crucial for timely and effective treatment.

Purpose of the Study:

  • To evaluate the efficacy of deep convolutional neural network (DCNN)-based features for distinguishing cardiac sarcoidosis (CS) from non-CS.
  • To assess if high-level DCNN features extracted from polar maps can improve CS classification accuracy.

Main Methods:

  • Utilized polar maps constructed from PET/CT images of 85 patients (33 CS, 52 non-CS).
  • Extracted high-level features using the Inception-v3 network and applied the ReliefF algorithm for classification.
  • Compared DCNN performance against standardized uptake value (SUV) and coefficient of variance (CoV) based methods.

Main Results:

  • The DCNN method with ReliefF achieved a sensitivity of 0.839, specificity of 0.870, and harmonic mean of 0.854.
  • Conventional SUVmax and CoV methods yielded lower performance metrics (SUVmax: 0.564, CoV: 0.699).
  • DCNN-based features demonstrated significantly better classification performance.

Conclusions:

  • DCNN-based high-level features show greater effectiveness in CS classification compared to conventional low-level feature analysis.
  • This AI-driven approach holds promise for improving the diagnostic accuracy of cardiac sarcoidosis.